f222eb2b08
SpacemiT X60: dct_unquantize_h263_inter_c: 417.8 ( 1.00x) dct_unquantize_h263_inter_rvv_i32: 66.0 ( 6.33x) dct_unquantize_h263_intra_c: 140.2 ( 1.00x) dct_unquantize_h263_intra_rvv_i32: 67.7 ( 2.07x) Note that the C benchmarks are not stable, depending heavily on the number of coefficients picked by the RNG. The R-V V benchmarks are however very stable and generally better than C's.
53 lines
1.5 KiB
ArmAsm
53 lines
1.5 KiB
ArmAsm
/*
|
|
* Copyright © 2024 Rémi Denis-Courmont.
|
|
*
|
|
* This file is part of FFmpeg.
|
|
*
|
|
* FFmpeg is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU Lesser General Public
|
|
* License as published by the Free Software Foundation; either
|
|
* version 2.1 of the License, or (at your option) any later version.
|
|
*
|
|
* FFmpeg is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
* Lesser General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU Lesser General Public
|
|
* License along with FFmpeg; if not, write to the Free Software
|
|
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
|
|
*/
|
|
|
|
#include "libavutil/riscv/asm.S"
|
|
|
|
func ff_h263_dct_unquantize_intra_rvv
|
|
lpad 0
|
|
addi a1, a1, 2
|
|
beqz a4, 1f
|
|
slli a3, a3, 1
|
|
mv a4, zero
|
|
j 2f
|
|
endfunc
|
|
|
|
func ff_h263_dct_unquantize_inter_rvv, zve32x, zba
|
|
lpad 0
|
|
addi a2, a2, 1
|
|
1:
|
|
addi a4, a3, -1
|
|
slli a3, a3, 1
|
|
ori a4, a4, 1
|
|
2:
|
|
vsetvli t0, a2, e16, m8, ta, mu
|
|
vle16.v v8, (a1)
|
|
sub a2, a2, t0
|
|
vmv.v.x v16, a4
|
|
vmslt.vi v0, v8, 0
|
|
vneg.v v16, v16, v0.t
|
|
vmsne.vi v0, v8, 0
|
|
vmadd.vx v8, a3, v16, v0.t
|
|
vse16.v v8, (a1)
|
|
sh1add a1, t0, a1
|
|
bnez a2, 2b
|
|
|
|
ret
|
|
endfunc
|